metadata
license: llama3.3
base_model: Steelskull/L3.3-Cu-Mai-R1-70b
pipeline_tag: text-generation
tags:
- mlx
Elypha/L3.3-Cu-Mai-R1-70b-Q8-mlx
The Model Elypha/L3.3-Cu-Mai-R1-70b-Q8-mlx was converted to MLX format from Steelskull/L3.3-Cu-Mai-R1-70b using mlx-lm version 0.21.5.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Elypha/L3.3-Cu-Mai-R1-70b-Q8-mlx")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)